.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/04_decision_boundary.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_auto_examples_04_decision_boundary.py>`
        to download the full example code.

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_04_decision_boundary.py:


Plotting the decision boundary
==============================

Plot the decision boundary a Soft Decision Tree learns on make_moons.

The boundary is smooth rather than axis-aligned and piecewise constant,
which is the visible difference between soft and hard splits.

Run with:
    python examples/04_decision_boundary.py

Writes examples/output/04_decision_boundary.png

.. GENERATED FROM PYTHON SOURCE LINES 15-55



.. image-sg:: /auto_examples/images/sphx_glr_04_decision_boundary_001.png
   :alt: SoftDecisionTree(depth=4) on make_moons, accuracy 0.840
   :srcset: /auto_examples/images/sphx_glr_04_decision_boundary_001.png
   :class: sphx-glr-single-img





.. code-block:: Python

    from pathlib import Path

    import matplotlib

    matplotlib.use("Agg")
    import matplotlib.pyplot as plt
    import numpy as np
    from sklearn.datasets import make_moons

    from neural_trees import SoftDecisionTree

    X, y = make_moons(n_samples=400, noise=0.2, random_state=42)

    model = SoftDecisionTree(depth=4, max_epochs=40, random_state=42)
    model.fit(X, y)

    x_min, x_max = X[:, 0].min() - 0.5, X[:, 0].max() + 0.5
    y_min, y_max = X[:, 1].min() - 0.5, X[:, 1].max() + 0.5
    xx, yy = np.meshgrid(
        np.linspace(x_min, x_max, 300), np.linspace(y_min, y_max, 300)
    )
    grid = np.c_[xx.ravel(), yy.ravel()]
    zz = model.predict_proba(grid)[:, 1].reshape(xx.shape)

    fig, ax = plt.subplots(figsize=(7, 5))
    contour = ax.contourf(xx, yy, zz, levels=20, cmap="RdBu_r", alpha=0.8)
    ax.contour(xx, yy, zz, levels=[0.5], colors="black", linewidths=1.2)
    ax.scatter(X[:, 0], X[:, 1], c=y, cmap="RdBu_r", edgecolors="k", s=25)
    ax.set_title(f"SoftDecisionTree(depth=4) on make_moons, accuracy {model.score(X, y):.3f}")
    fig.colorbar(contour, ax=ax, label="P(class 1)")

    # Writing a file only makes sense when this runs as a script. Inside the
    # documentation gallery there is no __file__ and the figure is captured directly.
    if "__file__" in globals():
        out_path = Path(__file__).parent / "output" / "04_decision_boundary.png"
        out_path.parent.mkdir(parents=True, exist_ok=True)
        fig.savefig(out_path, dpi=150, bbox_inches="tight")
        print(f"Saved {out_path}")
    else:
        plt.show()


.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 0.713 seconds)


.. _sphx_glr_download_auto_examples_04_decision_boundary.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: 04_decision_boundary.ipynb <04_decision_boundary.ipynb>`

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: 04_decision_boundary.py <04_decision_boundary.py>`

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: 04_decision_boundary.zip <04_decision_boundary.zip>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_